| ▲ | andes314 4 hours ago | |
Linear time attention doesn’t work, by principle. Dead end pursuit. Much great research on more efficient quadratic time inference | ||
| ▲ | smokel 3 hours ago | parent [-] | |
What about n log n? | ||
| ▲ | andes314 4 hours ago | |
Linear time attention doesn’t work, by principle. Dead end pursuit. Much great research on more efficient quadratic time inference | ||
| ▲ | smokel 3 hours ago | parent [-] | |
What about n log n? | ||